Modeling emotion for human-like behavior in future intelligent robots
This paper addresses the challenge of designing more human-like and socially capable robots by integrating neuroscience insights, though it is incremental as it reviews and proposes principles rather than presenting new empirical results.
This opinion paper reviews the current landscape of emotion modeling in robots, highlighting that existing artificial emotion proposals lack sufficient neuroscientific grounding, and argues for stronger integration of emotion-related processes to achieve human-like behavior in future intelligent machines.
Over the past decades, research in cognitive and affective neuroscience has emphasized that emotion is crucial for human intelligence and in fact inseparable from cognition. Concurrently, there has been growing interest in simulating and modeling emotion-related processes in robots and artificial agents. In this opinion paper, our goal is to provide a snapshot of the present landscape in emotion modeling and to show how neuroscience can help advance the current state of the art. We start with an overview of the existing literature on emotion modeling in three areas of research: affective computing, social robotics, and neurorobotics. Briefly summarizing the current state of knowledge on natural emotion, we then highlight how existing proposals in artificial emotion do not make sufficient contact with neuroscientific evidence. We conclude by providing a set of principles to help guide future research in artificial emotion and intelligent machines more generally. Overall, we argue that a stronger integration of emotion-related processes in robot models is critical for the design of human-like behavior in future intelligent machines. Such integration not only will contribute to the development of autonomous social machines capable of tackling real-world problems but would contribute to advancing understanding of human emotion.